Learning Deep and Wide Contextual Representations Using BERT for Statistical Parametric Speech Synthesis.
Ya-Jie ZhangZhen-Hua LingPublished in: ICDSP (2021)
Keyphrases
- speech synthesis
- learning algorithm
- learning tasks
- learning process
- speech recognition
- knowledge acquisition
- supervised learning
- contextual information
- machine learning
- wide range
- probabilistic model
- hidden markov models
- statistical analysis
- computer vision
- active learning
- statistical models
- learning problems
- learning scenarios
- learning scheme
- deep learning
- word processing
- reinforcement learning